Exponentially convergent stochastic k-PCA without variance reduction

NeurIPS 2019

Exponentially convergent stochastic k-PCA without variance reduction

Dec 12, 2019
|
41 views
|
Details
We present Matrix Krasulina, an algorithm for online k-PCA, by generalizing the classic Krasulina's method (Krasulina, 1969) from vector to matrix case. We show, both theoretically and empirically, that the algorithm naturally adapts to data low-rankness and converges exponentially fast to the ground-truth principal subspace. Notably, our result suggests that despite various recent efforts to accelerate the convergence of stochastic-gradient based methods by adding a O(n)-time variance reduction step, for the k-PCA problem, a truly online SGD variant suffices to achieve exponential convergence on intrinsically low-rank data. Speakers: Cheng Tang

Comments
loading...